Adaptive Bitrate Streaming Over Cellular Networks: Rate Adaptation and Data Savings Strategies

Abstract: Adaptive bitrate streaming (ABR) has become thede factotechnique for videostreaming over the Internet. Despite a flurry of techniques, achieving high quality ABRstreaming over cellular networks remains a tremendous challenge. First, the design ofan ABR scheme needs to balance conflicting Quality of Experience (QoE) metrics suchas video quality, quality changes, stalls and startup performance, which is even harderunder highly dynamic bandwidth in cellular network. Second, streaming providers havebeen moving towards using Variable Bitrate (VBR) encodings for the video content,which introduces new challenges for ABR streaming, whose nature and implicationsare little understood. Third, mobile video streaming consumes a lot of data. Althoughmany video and network providers currently offer data saving options, the existingpractices are suboptimal in QoE and resource usage. Last, when the audio and videotracks are stored separately, video and audio rate adaptation needs to be dynamicallycoordinated to achieve good overall streaming experience, which presents interestingchallenges while, somewhat surprisingly, has received little attention by the researchcommunity. In this dissertation, we tackle each of the above four challenges.